Package smile.deep.optimizer

Class SGD

java.lang.Object

smile.deep.optimizer.SGD

All Implemented Interfaces:

Serializable, Optimizer

public class SGD
extends Object
implements Optimizer

Stochastic gradient descent (with momentum) optimizer.

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
SGD()	Constructor.
SGD(smile.math.TimeFunction learningRate)	Constructor.
SGD(smile.math.TimeFunction learningRate, smile.math.TimeFunction momentum)	Constructor.

Method Summary

Modifier and Type	Method	Description
String	toString()
void	update(Layer layer, int m, int t)	Updates a layer.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Details

SGD

public SGD()

Constructor.

SGD

public SGD(smile.math.TimeFunction learningRate)

Constructor.

Parameters:

learningRate - the learning rate.

SGD

public SGD(smile.math.TimeFunction learningRate,
 smile.math.TimeFunction momentum)

Constructor.

Parameters:

learningRate - the learning rate.

momentum - the momentum.

Method Details

toString

public String toString()

Overrides:

toString in class Object

update

public void update(Layer layer,
 int m,
 int t)

Description copied from interface: Optimizer

Updates a layer.

Specified by:

update in interface Optimizer

Parameters:

layer - a neural network layer.

m - the size of mini-batch.

t - the time step, i.e. the number of training iterations so far.